AMDGPU: update GFX11 wmma hazards

One V_NOP od unrelated VALU instruction in between is required for
correctness when matrix A or B of current WMMA instruction overlaps
with matrix D of previous WMMA instruction.
Remaining cases of WMMA operand overlaps are handled by the hardware
and do not require handling in hazard recognizer.

Hardware may stall in cases where:
- matrix C of current WMMA instruction overlaps with
  matrix D of previous WMMA instruction
- VALU instruction reads matrix D of previous WMMA instruction
- matrix A,B or C of WMMA instruction reads result of previous
  VALU instruction

Author: petar-avramovic

llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp

@@ -1713,8 +1713,8 @@ bool GCNHazardRecognizer::fixWMMAHazards(MachineInstr *MI) {
     if (!SIInstrInfo::isWMMA(I))
       return false;
 
-    // Src0 or Src1 of the current wmma instruction overlaps with the dest of
-    // the previous wmma.
+    // Src0(matrix A) or Src1(matrix B) of the current wmma instruction overlaps
+    // with the dest(matrix D) of the previous wmma.
     const Register CurSrc0Reg =
         TII->getNamedOperand(*MI, AMDGPU::OpName::src0)->getReg();
     const Register CurSrc1Reg =
@@ -1728,25 +1728,6 @@ bool GCNHazardRecognizer::fixWMMAHazards(MachineInstr *MI) {
       return true;
     }
 
-    // Src2 of the current wmma instruction overlaps with the dest of the
-    // previous wmma.
-    const MachineOperand *Src2 =
-        TII->getNamedOperand(*MI, AMDGPU::OpName::src2);
-    const Register CurSrc2Reg = Src2->isReg() ? Src2->getReg() : Register();
-
-    if (CurSrc2Reg != AMDGPU::NoRegister &&
-        TRI->regsOverlap(PrevDstReg, CurSrc2Reg)) {
-
-      const MachineOperand *Src2Mods =
-          TII->getNamedOperand(*MI, AMDGPU::OpName::src2_modifiers);
-      const bool NoSrc2Mods =
-          (Src2Mods->getImm() & (SISrcMods::NEG | SISrcMods::NEG_HI)) == 0;
-      // Exception: there is no hazard if the wmma instructions are of the same
-      // type and there is no input modifier on src2 of the current instruction.
-      return !(NoSrc2Mods && (TII->pseudoToMCOpcode(I.getOpcode()) ==
-                              TII->pseudoToMCOpcode(MI->getOpcode())));
-    }
-
     return false;
   };